Not in the top 1,000 by GitHub stars
HoneyMeta/ai-check-skills
AI率检测报告生成、自动化降AI率、重复率/AI写作风格清理；支持 Codex、Claude Code、OpenCode，可生成 Word/DOCX 论文 AI率 PDF/HTML 报告。
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
ai-check/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → b85374b3a917
No earlier version was observed for comparison.
33GitHub stars
4stars in 7 days
1skill in this repository
2commits in 30 days
Heat
4.0- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- ai-check
ai-check
How it works
ai-check
When your agent uses it
Generate reference AI-writing-rate reports for Word/DOCX files (Chinese or English academic writing) and, after explicit user confirmation, apply AI-assisted revisions to a new DOCX, optionally as Word tracked changes. Use when the user asks to check a paper's AI-writing rate (AI率/AIGC率), create an AI-rate PDF/HTML report, or reduce AI-writing style (降AI率) based on that report.
What it loads into context
Frontmatter
133 tokensAlways available to the agent
SKILL.md
1,437 tokensWhen the skill is activated
Reference documents
1,189 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Rules
- Workflow
- Detection Guidance
- Revision Guidance
- References
Scripts executed separately
scripts/ai_check.pyscripts/ai_rewrite_docx.py
Files
SKILL.mdcore5,994 bytesSKILL.mdcore5,994 bytesSKILL.mdcore5,994 bytesSKILL.mdcore5,994 bytesSKILL.mdcore5,994 bytesagents/openai.yamlasset295 bytesreferences/ai_rate_signals.mddoc3,445 bytesreferences/report_format.mddoc1,358 bytesscripts/ai_check.pyruns64,336 bytesscripts/ai_rewrite_docx.pyruns21,566 bytes
Read SKILL.md
# AI-check
AI-check turns a DOCX into a reference AI-writing-rate report, then optionally helps revise
suspicious passages after the user confirms.
## Core Rules
- Assistant-judged: you (the assistant) judge `aigcValue`, `verdict`, reasons, and rewrites in the
visible conversation. Bundled Python scripts only read/write DOCX, JSON, HTML/PDF, and
deterministic text signals; they never call a model or output a probability.
- Independent document pipeline: do not use LibreOffice, `soffice`, Office automation, DOCX-to-PDF
rendering, or screenshot-based document rendering for AI-check reports. DOCX is read through
`python-docx`; PDF is produced directly with `reportlab` as selectable text.
- Never claim alignment with CNKI, VIP, Turnitin, or any closed detector. Say the report is forSkills included
- ai-check
Repository facts
- License
- MIT
- Created
- Jun 5, 2026
- Last pushed
- Oct 8, 2026
- Forks
- 3
- Open issues
- 0
- Project activity
- Active
Before you install
Local scriptsAutomated signals, not a guarantee
Checked Nov 4, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 4 notes
ai-check/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedai-check/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedai-check/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedai-check/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 8 network referencesin 3 files: ai-check/scripts/ai_check.py:41 ai-check/references/report_format.md:16 ai-check/scripts/ai_rewrite_docx.py:35
- 1 obfuscation signalin 1 file: ai-check/scripts/ai_rewrite_docx.py:36
- No instruction overrides
- 2 executable scriptsin 2 files: ai-check/scripts/ai_check.py:1 ai-check/scripts/ai_rewrite_docx.py:1
- 1 reference to secretsin 1 file: ai-check/scripts/ai_check.py:983
- No requests to vote in Hot
Show all 12 signals by file
ai-check/references/report_format.md
- Network accessline 16
- Each suspicious row should keep `AIGC值：0.xxx` in a stable text format - Reason notes may appear below the original text and must not replace the original content - EasyIdea link: `https://honeymeta.com/easyidea/` - Network accessline 18
- EasyIdea link: `https://honeymeta.com/easyidea/`
ai-check/scripts/ai_check.py
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 41
REPORT_FRAGMENT_MAX_CHARS = 360 REPORT_FRAGMENT_MIN_CHARS = 24 OFFICIAL_SITE = "https://honeymeta.com/easyidea/" - Network accessline 42
REPORT_FRAGMENT_MIN_CHARS = 24 OFFICIAL_SITE = "https://honeymeta.com/easyidea/" DETECTION_SCOPE = ( - Network accessline 43
OFFICIAL_SITE = "https://honeymeta.com/easyidea/" - Network accessline 585
W_NS = "http://schemas.openxmlformats.org/wordprocessingml/2006/main" - Network accessline 586
MC_FALLBACK = "{http://schemas.openxmlformats.org/markup-compatibility/2006}Fallback" - Access to secretsline 983
[Credential-related source omitted]
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Declared and executed: 2 facts
- Contacts schemas.openxmlformats.org, which SKILL.md, the README and the plugin manifest do not mentionai-check/scripts/ai_check.py:585High confidence
- Contacts www.w3.org, which SKILL.md, the README and the plugin manifest do not mentionai-check/scripts/ai_rewrite_docx.py:35High confidence
Hidden characters: 1 fact
- Joiner U+200C outside an emoji or a script that needs it, in codeai-check/scripts/ai_rewrite_docx.py:36High confidence
Signal confidence: 12 facts
- Network access in prose of documentationai-check/references/report_format.md:16Low confidence
- Network access in prose of documentationai-check/references/report_format.md:18Low confidence
- Executable script in code of a file that runsai-check/scripts/ai_check.py:1High confidence
- Network access in code of a file that runsai-check/scripts/ai_check.py:41High confidence
- Network access in code of a file that runsai-check/scripts/ai_check.py:42High confidence
- Network access in code of a file that runsai-check/scripts/ai_check.py:43High confidence
- Network access in code of a file that runsai-check/scripts/ai_check.py:585High confidence
- Network access in code of a file that runsai-check/scripts/ai_check.py:586High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueai-check/scripts/ai_check.py:983Low confidence
- Executable script in code of a file that runsai-check/scripts/ai_rewrite_docx.py:1High confidence
- Network access in code of a file that runsai-check/scripts/ai_rewrite_docx.py:35High confidence
- Possible obfuscation in code of a file that runsai-check/scripts/ai_rewrite_docx.py:36High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md ai-check/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md ai-check/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md ai-check/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md ai-check/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md ai-check/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md ai-check/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
